English
Related papers

Related papers: Regularization of ill-posed point neuron models

200 papers

As first-order optimization methods become the method of choice for solving large-scale optimization problems, optimization solvers based on first-order algorithms are being built. Such general-purpose solvers must robustly detect…

Optimization and Control · Mathematics 2023-03-29 Jisun Park , Ernest K. Ryu

One way of improving the behavior of finite element schemes for classical, time-dependent Maxwell's equations, is to render them from their hyperbolic character to elliptic form. This paper is devoted to the study of the stabilized linear…

Numerical Analysis · Mathematics 2024-09-23 M. Asadzadeh , L. Beilina

We study Tikhonov regularization for certain classes of non-linear ill-posed operator equations in Hilbert space. Emphasis is on the case where the solution smoothness fails to have a finite penalty value, as in the preceding study…

Numerical Analysis · Mathematics 2019-04-04 Bernd Hofmann , Peter Mathé

A recent analysis of a model of iterative neural network in Hilbert spaces established fundamental properties of such networks, such as existence of the fixed points sets, convergence analysis, and Lipschitz continuity. Building on these…

Machine Learning · Computer Science 2019-08-20 Tomasz Piotrowski , Krzysztof Rykaczewski

We are interested in the classical ill-posed Cauchy problem for the Laplace equation. One method to approximate the solution associated with compatible data consists in considering a family of regularized well-posed problems depending on a…

Analysis of PDEs · Mathematics 2019-06-21 Laurent Bourgeois , Lucas Chesnel

It was recently proved in [Corwin-Shen, 2016] that under weak asymmetry scaling, the height functions for open ASEP on the half-line and on a bounded interval converge to the Hopf-Cole solution of the KPZ equation with Neumann boundary…

Probability · Mathematics 2018-09-26 Shalin Parekh

Based on the powerful tool of variational inequalities, in recent papers convergence rates results on $\ell^1$-regularization for ill-posed inverse problems have been formulated in infinite dimensional spaces under the condition that the…

Functional Analysis · Mathematics 2015-05-18 Jens Flemming , Bernd Hofmann , Ivan Veselic

We investigate a coordinate-free model of flame fronts introduced by Frankel and Sivashinsky; this model has a parameter $\alpha$ which relates to how unstable the front might be. We first prove short-time well-posedness of the…

Analysis of PDEs · Mathematics 2020-10-05 David M. Ambrose , Fazel Hadadifard , J. Douglas Wright

We investigate Strichartz estimates for the nonlinear beam equation with initial data $f\in\dot{H}^s, g\in\dot{H}^{s-2}$ and $f\in H^s, g\in H^{s-2}$. We extend results of H. Lindblad and C. D.Sogge [10] and T. Cazenave and F. B. Weissler…

Analysis of PDEs · Mathematics 2013-06-28 Shuxin Wang

A recent result characterizes the fully order reversing operators acting on the class of lower semicontinuous proper convex functions in a real Banach space as certain linear deformations of the Legendre-Fenchel transform. Motivated by the…

Classical Analysis and ODEs · Mathematics 2019-04-09 Alfredo N. Iusem , Daniel Reem , Simeon Reich

We establish and prove a fixed point theorem from which some sufficient conditions on the existence of positive almost periodic solutions for a model of hematopoiesis with oscillatory circulation loss rate are deduced. Some particular…

Classical Analysis and ODEs · Mathematics 2018-01-24 Rocío Balderrama

The success of reinforcement learning (RL) crucially depends on effective function approximation when dealing with complex ground-truth models. Existing sample-efficient RL algorithms primarily employ three approaches to function…

Machine Learning · Computer Science 2024-01-09 Yunfan Li , Lin Yang

Local well-posedness is established for a highly nonlocal nonlinear diffusion-adhesion system for bounded initial values with small support. Macroscopic systems of this kind were previously obtained by the authors through upscaling in [32]…

Analysis of PDEs · Mathematics 2025-05-16 Mabel Lizzy Rajendran , Anna Zhigun

Overdetermined systems of first kind integral equations appear in many applications. When the right-hand side is discretized, the resulting finite-data problem is ill-posed and admits infinitely many solutions. We propose a numerical method…

Numerical Analysis · Mathematics 2023-07-26 Patricia Díaz de Alba , Luisa Fermo , Federica Pes , Giuseppe Rodriguez

We study random integer-valued Lipschitz functions on regular trees. It was shown by Peled, Samotij and Yehudayoff that such functions are localized, however, finer questions about the structure of Gibbs measures remain unanswered. Our main…

Probability · Mathematics 2024-10-10 Nathaniel Butler , Kesav Krishnan , Gourab Ray , Yinon Spinka

We provide general conditions ensuring that the value functions of some nonlinear stopping problems with finite horizon converge to the value functions of the corresponding problems with infinite horizon. Our result can be formulated as…

Probability · Mathematics 2022-10-28 Tomasz Klimsiak , Andrzej Rozkosz

This paper investigates solution stability properties of unregularized tracking-type optimal control problems constrained by the Boussinesq system. In our model, the controls may appear linearly and distributed in both of the equations that…

Optimization and Control · Mathematics 2024-02-13 Nicolai Jork , John Sebastian H. Simon

We show local well-posedness for the Mullins-Sekerka system with ninety degree angle boundary contact. We will describe the motion of the moving interface by a height function over a fixed reference surface. Using the theory of maximal…

Analysis of PDEs · Mathematics 2019-02-12 Helmut Abels , Maximilian Rauchecker , Mathias Wilke

We obtain estimation error rates and sharp oracle inequalities for regularization procedures of the form \begin{equation*} \hat f \in argmin_{f\in F}\left(\frac{1}{N}\sum_{i=1}^N\ell(f(X_i), Y_i)+\lambda \|f\|\right) \end{equation*} when…

Statistics Theory · Mathematics 2017-02-08 Pierre Alquier , Vincent Cottet , Guillaume Lecué

The inner alignment problem, which asserts whether an arbitrary artificial intelligence (AI) model satisfices a non-trivial alignment function of its outputs given its inputs, is undecidable. This is rigorously proved by Rice's theorem,…